Blog
Introducing Replit DesignThe next era of design, for everyone
Published:
Jul 29, 2026Updated:
Aug 4, 2026
The Replit Team
A new creative class is rising: people who see an idea in their mind and refuse to wait to make it.
Today, we’re launching Replit Design, a new creative suite where anyone can shape what they see as fast as they can think it.
Replit Design is the fastest way to go from idea to design. Ambient Intelligence guides and inspires you at every step, and because everything lives on Replit, there are no handoffs, exports, or rebuilds that cause you to lose the beauty of what you created.
You don’t need to be a designer. You just need to know what you want to bring to life.
Create with your choice of the world’s leading models for design, including Claude, GPT-5, Gemini, Kimi, and GLM.
The next era of design for the new class of creatives
We hosted creatives at vibecon last month in New York, where people turned memories into perfume, movement into light, and ideas into experiences they could hold, wear and enter.
In early access, many of this new creative class put Replit Design to work on everything from marketing assets to real published apps and sites.
Here’s some of what they made.
“As a founder of a brand strategy agency, I have a very specific eye for design. Most AI tools produce something generic that I’d never put my name on. Replit Design truly surprised me. I’m genuinely impressed, and I’m only just getting started with it.” Darby IRL
“I love that Replit lets me focus on creating instead of getting blocked by development. It’s empowered me to launch projects I have attempted before.” Agatha (Designely)
How Replit Design works
Ambient Intelligence unlocks the designer in all of us
Replit Design re-invents how AI design works, giving every idea a way to arrive in the world with the same energy, ambition, and emotion it had in your mind. At its core is what we call Ambient Intelligence.
AI in code has already made the leap from “complete this line of code” to “build this app for me.” Ambient intelligence brings this leap to design. At every step, you’ll see suggested variations and progressions that you can accept with a single click, turning your idea over in different lights until the thing on screen matches (or beats) the thing in your head.
Templates as ingredients, not just starting points
We’ve all had moments when an idea runs into a wall. Replit Design is built to get you over it.
Other AI design tools treat templates as a starting point; in Replit Design they’re an ingredient you can add at any moment. Drop one in at any time, from a library of hundreds made by real designers, to bring fresh inspiration into a project mid-flight. Start from scratch, start from a template, or remix several into something new until it feels like yours.
A moodboard on demand
Designers collect inspiration for a living: screenshots, saved links, moodboards. Now everyone gets to start there.
We built Mobbin into Replit Design: the world’s largest UI and UX reference library, trusted by over two million designers and updated weekly with how the best designs work right now. And in an industry first, everyone gets access. No Mobbin account required; it’s just there, wired in.
To use it, just describe what you want to create, and Replit Design draws from more than 600,000 real-world screens from over 1,000 apps to turn your idea into a finished app or site.
Your brand, everywhere, in one click
AI design today is fragmented. Prompt in one tool, refine in another, publish in a third. Every handoff strips something out: the colors drift, the type resets, the details that made it yours get lost in translation. What arrives at the end is a watered-down version of what you started with.
Replit Design comes with design systems built in. Upload yours or create one from scratch, and everything you make, on every screen, snaps to your brand in a single click.
Just hit publish, people are going to love it.
Get started
This post began with a new creative class: people who see an idea and refuse to wait to make it. If that’s you, the waiting is over.
Replit Design is live today for every user. And to mark it, we’re throwing a Designathon, with over $50,000 in cash and Replit credits for the designs that stop us in our tracks.
We can't wait to see what you create!
Start at https://replit.com/design.
Want to go deeper? We’re talking process today at 2pm PDT (9pm GMT) on X with the team that built Design.
For existing Canvas users, Replit Design is its next evolution. Your Canvas projects are all here, with a lot more capability.
More
Sep 29, 2026Free the models: Harness design at the frontier
Model routers are everywhere right now, but they have a fundamental limitation. No matter if based on advanced heuristics or a small model that reads each turn and picks which LLM to use, a router will always be less capable than the model it’s choosing for. Replit Agent lets the model decide instead. The main agent, or core loop, chooses its subagents’ tier and effort, and adjusts its own as the task unfolds. Given that freedom, GPT-6 Astra hands routine implementation to less costly subagents and decides for itself where its tokens are worth spending. On both DeepSWE and Terminal-Bench, Replit Agent is Pareto-efficient against Astra on its own: no published Astra baseline costs less and scores higher. It also beats a sidekick architecture, the same setup with one long-lived worker, by 11 and 16 points. Why we scaffold less Every model release invalidates assumptions baked into the harness. As models become stronger at long-horizon tasks, they don’t need as much scaffolding at the harness layer. In practice, we’ve observed them lean more towards delegation on their own: using subagents for context management and parallelism. Recent breakthroughs, Navier–Stokes among them, came in part from coordinating swarms of agents powered by frontier models [1]. But the frontier is jagged. The strongest coding model is not necessarily the strongest at designing UIs or making slides, nor the best at writing emails. So we design our harness to let each model work its own way, with the guardrails it still needs and quality at minimum cost as the goal.
Sep 10, 2026Databricks Integration is Now Available with Native Lakebase Support
The Replit | Databricks integration gives enterprise teams a faster path to utilizing governed data for production-ready applications. Today, we’re excited to announce the integration is generally available alongside a new capability: native Databricks Lakebase support. This builds on the foundation introduced from our public preview announcement this past June. The result is one seamless path from idea to production: Replit accelerates application creation, while Databricks hosts and provides governed access and security to live enterprise data. Through Lakebase, Databricks also delivers a managed database for storing and updating application data. With native Lakebase support, teams can build full-stack, context-rich apps that combine live Databricks warehouse data with information created and updated through the app. When an app built with Replit is ready to deploy, Replit Agent automatically provisions its Lakebase database, eliminating the need for manual setup. New Capabilities for a Faster, Safer Launch Automated Preview Deploys: Test your apps before they go live. Replit automatically creates a separate preview environment that keeps test data isolated from live business data in Databricks, giving teams a safe place to build, review changes, and make adjustments.
Aug 3, 2026AI adoption starts with truth
The semantic layer is the foundation AI adoption is limited by trust. A user who gets burned by a confidently wrong answer will double-check the next one, eventually routing consequential work around the system entirely. Once that happens, AI remains a tool at the edges rather than infrastructure at the center… useful, but never trusted with the workflows where its value compounds. Before a company can benefit from more capable agents, those agents need a reliable way to know what the company considers true. A semantic layer tells an agent which tables are sources of truth and how they relate. That's the floor. It is necessary, and it isn't sufficient. A semantic layer is not plumbing. It is the first act of governance for an AI-native company: the shared definitions of the business, the canonical metrics, the sources of truth, and the relationships an agent is allowed to rely on. Without it, an agent does not have a data problem. It has a language problem: several tables can each look plausible, and the model has no grounded way to know which one means "revenue," "active user," or "customer." Getting that floor right changes the shape of everything above it. A semantic layer is not the product; it is the shared contract that lets a company safely add a system of specialized capabilities instead of one generic chatbot. Once an agent can ground itself in the right entities, metrics, and relationships, it can reliably run multi-step workflows, call focused tools, retain reviewed knowledge across runs, reuse validation and analysis code, and operate through durable services where work already happens.